© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 253002
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     來
    0.56
     하시
    0.50
    енти
    0.48
     transparen
    0.48
     學
    0.47
     lega
    0.46
     caratteristiche
    0.46
     會
    0.46
     granit
    0.46
     abat
    0.46
    POSITIVE LOGITS
     December
    0.47
    保湿
    0.46
    जनन
    0.45
     moistur
    0.45
     ब्रेस्ट
    0.44
    महिलाओं
    0.44
     ट्रेंड
    0.43
    dades
    0.42
     newborns
    0.42
     Vitamins
    0.42
    Activations Density 0.000%

    No Known Activations